Social Cooperation in Conversational AI Agents

TL;DR

This paper discusses enhancing conversational AI agents by modeling human social intelligence to improve long-term interaction capabilities, addressing current limitations of short-term training.

Contribution

It introduces a mathematical framework for modeling human social strategies to enable AI agents to better maintain long-term relationships.

Findings

Proposes a game-theoretic approach to model social interactions.

Highlights the importance of long-term relationship modeling for AI.

Suggests new objectives for optimizing AI agents based on social strategies.

Abstract

The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific research. A major challenge with such agents is that, by necessity, they are trained by observing relatively short-term interactions with humans. Such models can fail to generalize to long-term interactions, for example, interactions where a user has repeatedly corrected mistakes on the part of the agent. In this work, we argue that these challenges can be overcome by explicitly modeling humans' social intelligence, that is, their ability to build and maintain long-term relationships with other agents whose behavior cannot always be predicted. By mathematically modeling the strategies humans use to communicate and reason about one another over long periods of time, we may be able to derive new game theoretic objectives against which LLMs and future AI agents may be optimized.